Report · marked 25 Aug 2026
vercel-labs/agent-browser
Solid foundations, held back in a few specific places.
Rust · 41,327 stars · 463 files · branch main
76
/100
B+
Instructions
27/27Whether the repo tells an agent how to behave before it starts guessing. Full marks.Setup
16/18Whether an agent can install the project and get it running without a human. Losing marks on environment config.Verification loop
8/22Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy. Losing marks on tests exist and test command is discoverable.Context economy
14/20Whether the repo fits in a context window, or fights it. Losing marks on file sizes fit in context.Navigability
9/10How quickly anything new can orient itself. Losing marks on repository description.
Higher is better. Accent marks what is costing you most.
Fix these first
01
Test command is discoverable
Add a `test` script or a `test` target that runs the whole suite with no arguments. The convention is the interface — an agent tries `npm test` and `make test` before it tries reading your CI config.
02
File sizes fit in context
A single file that fills the context window forces an agent to work from fragments, and it will confidently edit code it never saw. Splitting the worst offenders pays for itself immediately.
03
Tests exist
Coverage is thin enough that an agent can break real behavior and still see green.
The full marking
Every deduction below names the file or setting it came from.
Instructions 27/27 A+
Whether the repo tells an agent how to behave before it starts guessing.
✓Agent instruction file
12/12
AGENTS.md is present, which is the format the most tools read.
✓Instruction quality
12/12
Specific enough that an agent can act on it.
9,289 characters, a workable length
names the actual commands to run
uses headings, so an agent can skim it
includes copyable code blocks
✓README as an entry point
3/3
README has a clear getting-started section.
Setup 16/18 A
Whether an agent can install the project and get it running without a human.
✓Deterministic install
6/6
pnpm-lock.yaml pins the dependency tree.
Found pnpm-lock.yaml
✓Discoverable commands
6/6
Commands are declared where an agent will look for them.
package.json scripts (version:sync, version, build:native, build:linux, build:macos, build:windows…)
scripts/ directory
✗Environment config
2/4
Env vars are mentioned in the README but there's no example file to copy.
Add a .env.example listing every variable with a safe placeholder value. It's the cheapest possible fix and it unblocks the whole first run.
✓Pinned runtime version
2/2
The language runtime version is pinned.
Found .node-version
–Reproducible environment
n/a
Not applicable — a library doesn't need a container to be worked on.
Verification loop 8/22 D
Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy.
✗Tests exist
4/8
6 test files against 309 source files.
Coverage is thin enough that an agent can break real behavior and still see green.
e.g. cli/tests/doctor_cli.rs, cli/tests/pin_tab_cli.rs, packages/@agent-browser/eve/test/extension.test.mjs
✗Test command is discoverable
0/7
There's no obvious way to run the tests. Even if tests exist, an agent won't reliably find the entry point.
Add a `test` script or a `test` target that runs the whole suite with no arguments. The convention is the interface — an agent tries `npm test` and `make test` before it tries reading your CI config.
✓Continuous integration
4/4
2 GitHub Actions workflows define what "passing" means.
✗Lint and format rules
0/3
No linter or formatter config. Style is tribal knowledge, so agent output will drift from yours.
A formatter config is the cheapest way to stop reviewing whitespace in agent diffs. It moves style from opinion to a command.
–Static type checking
n/a
Not applicable — the Rust compiler type checks every build.
Context economy 14/20 B+
Whether the repo fits in a context window, or fights it.
✓No committed build output
6/6
No generated directories committed.
✓.gitignore hygiene
3/3
.gitignore covers 40 patterns.
✗File sizes fit in context
0/6
7 source files are over 100KB.
A single file that fills the context window forces an agent to work from fragments, and it will confidently edit code it never saw. Splitting the worst offenders pays for itself immediately.
cli/src/native/actions.rs — 554KB
cli/src/native/e2e_tests.rs — 274KB
cli/src/commands.rs — 221KB
✓Repository weight
5/5
About 20.3MB checked out, which is comfortable.
Here is your AGENTS.md
Drafted from what is actually in this repository: the install
command from your lockfile, the commands you already declare, your real directory layout. Anything
marked TODO needs a person. Save it at the root as AGENTS.md.
# AGENTS.md Browser automation CLI for AI agents ## Setup ``` pnpm install ``` ## Commands ``` pnpm version:sync pnpm version pnpm build:native pnpm build:linux pnpm build:macos pnpm build:windows pnpm build:all-platforms pnpm build:docker ``` ## Layout - `cli/` 80 source files - `packages/` 74 source files - `docs/` 68 source files - `examples/` 59 source files - `evals/` 12 source files - `scripts/` 10 source files ## Conventions - Tests live alongside the code they cover, following `cli/tests/doctor_cli.rs`. - CI defines what passing means. See `.github/workflows/ci.yml`, and keep it green. - TODO: add the two or three conventions a newcomer always gets wrong here. ## Gotchas - `cli/src/native/actions.rs` is 554KB. It will not fit comfortably in context, so read it in parts. --- Drafted by agentreadme.com from what is in this repository. Everything marked TODO needs a human. Check it in as AGENTS.md at the root.
Open the raw markdown
or
curl -o AGENTS.md agentreadme.com/draft/vercel-labs/agent-browser.md
Show the mark
The badge re-checks daily, so it keeps up as the repository changes. Use mark again to force it now.
[](https://agentreadme.com/vercel-labs/agent-browser)Other Rust repositories, marked
Think this mark is wrong?
Every deduction above names the file it came from, so this can be settled by looking. If a check missed something, that is a rule worth fixing.